AutoGLM ASR MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| AUTOGLM_ASR_MODEL | No | ASR model name | glm-asr-2512 |
| AUTOGLM_ASR_API_KEY | Yes | Your Zhipu API key | |
| AUTOGLM_ASR_API_BASE | No | API endpoint | https://open.bigmodel.cn/api/paas/v4/audio/transcriptions |
| AUTOGLM_ASR_MAX_CONCURRENCY | No | Default concurrency | 5 |
| AUTOGLM_ASR_CONTEXT_MAX_CHARS | No | Max context size passed between chunks | 2000 |
| AUTOGLM_ASR_MAX_CHUNK_DURATION | No | Max chunk duration (seconds) | 25 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| transcribe_audioA | Transcribe an audio file to text using AutoGLM ASR. Supports: mp3, wav, m4a, flac, ogg, webm Features:
Args: audio_path: Absolute path to the audio file context_mode: "sliding" (recommended), "none" (fastest), or "full_serial" (best quality but slow) max_concurrency: Max parallel API requests (default: 5) Returns: Full transcription text with timing segments |
| get_audio_infoA | Get information about an audio file (duration, format). Use this to check audio length before transcription. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 2 tools
Each tool has a clearly distinct purpose: transcribe_audio performs the core speech-to-text conversion, while get_audio_info retrieves file metadata for pre-checking. There is no overlap or ambiguity between them.
Both tools follow a consistent verb_noun snake_case convention (transcribe_audio, get_audio_info), making the API predictable and easy to navigate.
The server has only 2 tools, which feels slightly thin for a dedicated ASR service. However, the tools cover the essential workflow (transcription + metadata check), so the count is not inappropriate.
The core transcription workflow is fully covered, and get_audio_info enables users to verify audio properties before transcribing. Minor gaps such as listing supported formats or job management exist, but these are not critical for the server's stated purpose.